Related papers: CertainNet: Sampling-free Uncertainty Estimation f…
Uncertainty in control and perception poses challenges for autonomous vehicle navigation in unstructured environments, leading to navigation failures and potential vehicle damage. This paper introduces a framework that minimizes control and…
Motion prediction of vehicles is critical but challenging due to the uncertainties in complex environments and the limited visibility caused by occlusions and limited sensor ranges. In this paper, we study a new task, safety-aware motion…
Reliable perception is fundamental for safety critical decision making in autonomous driving. Yet, vision based object detector neural networks remain vulnerable to uncertainty arising from issues such as data bias and distributional…
We argue that object detectors in the safety critical domain should prioritize detection of objects that are most likely to interfere with the actions of the autonomous actor. Especially, this applies to objects that can impact the actor's…
The availability of real-world datasets is the prerequisite for developing object detection methods for autonomous driving. While ambiguity exists in object labels due to error-prone annotation process or sensor observation noises, current…
Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy. However, those methods overlook the gap between network accuracy and prediction confidence, known as the confidence…
In a world where more decisions are made using artificial intelligence, it is of utmost importance to ensure these decisions are well-grounded. Neural networks are the modern building blocks for artificial intelligence. Modern neural…
This work tackles the unsupervised cross-domain object detection problem which aims to generalize a pre-trained object detector to a new target domain without labels. We propose an uncertainty-aware model adaptation method, which is based…
The high dynamics and heterogeneous interactions in the complicated urban systems have raised the issue of uncertainty quantification in spatiotemporal human mobility, to support critical decision-makings in risk-aware web applications such…
Accurate sensor calibration is crucial for autonomous systems, yet its uncertainty quantification remains underexplored. We present the first approach to integrate uncertainty awareness into online extrinsic calibration, combining Monte…
The tracking-by-detection paradigm is the mainstream in multi-object tracking, associating tracks to the predictions of an object detector. Although exhibiting uncertainty through a confidence score, these predictions do not capture the…
The inherent ambiguity in ground-truth annotations of 3D bounding boxes, caused by occlusions, signal missing, or manual annotation errors, can confuse deep 3D object detectors during training, thus deteriorating detection accuracy.…
Active learning has emerged as a promising approach to reduce the substantial annotation burden in 3D object detection tasks, spurring several initiatives in outdoor environments. However, its application in indoor environments remains…
Place recognition is key to Simultaneous Localization and Mapping (SLAM) and spatial perception. However, a place recognition in the wild often suffers from erroneous predictions due to image variations, e.g., changing viewpoints and street…
We consider the problem of uncertainty estimation in the context of (non-Bayesian) deep neural classification. In this context, all known methods are based on extracting uncertainty signals from a trained network optimized to solve the…
Seismic inversion is essential for geophysical exploration and geological assessment, but it is inherently subject to significant uncertainty. This uncertainty stems primarily from the limited information provided by observed seismic data,…
Uncertainty estimates of modern neuronal networks provide additional information next to the computed predictions and are thus expected to improve the understanding of the underlying model. Reliable uncertainties are particularly…
We present a sampling-free approach for computing the epistemic uncertainty of a neural network. Epistemic uncertainty is an important quantity for the deployment of deep neural networks in safety-critical applications, since it represents…
In the field of deep learning based computer vision, the development of deep object detection has led to unique paradigms (e.g., two-stage or set-based) and architectures (e.g., Faster-RCNN or DETR) which enable outstanding performance on…
We present an online and data-driven uncertainty quantification method to enable the development of safe human-robot collaboration applications. Safety and risk assessment of systems are strongly correlated with the accuracy of…